search

K-H-Ismail / Dilated-Convolution-with-Learnable-Spacings-PyTorch

[ICLR 2023] "Dilated convolution with learnable spacings" Ismail Khalfaoui Hassani, Thomas Pellegrini and Timothée Masquelier
MIT License
57 stars 5 forks source link

Where can I obtain the pre-trained model of ResNet trained with DCLS #3

Closed GluttonK closed 1 year ago

GluttonK commented 1 year ago

In your paper , I saw a result of ResNet50-dcls given besides the ConvNeXt-dcls. But I didn't find the trained model. If I need to train it by myself,Could you give the setting about it?Thank you

K-H-Ismail commented 1 year ago

Hello,

Here is a link with the best checkpoint for the two resnet-dcls runs of the paper along with the configs, summary and args used at that time. We used timm and a light training config for resnet (A3-config described in this paper).

link to the checkpoints

Besides, this last checkpoints use the v0 version of DCLS that uses bilinear interpolation. We discovered that a better interpolation (Gaussian) could be used instead please refer to this paper. We encourage you, if you want to do further investigations, to retrain using this last interpolation technique. More details are provided in this short blog post along with a script to replace all your convolutions with DCLS ones (see medium story).

We abondonned the research on architectures that do not use depthwise separable convolutions because implementing a dialted kernel of size 7 and higher is prohibitive in time if we don't use depthwise separable convolutions along with depthwise implicit gemm method link to the code of this method and original paper. Maybe you could investigate ResNeXt or ConvNeXt (as we did in our paper) as they use depthwise separable convs.

GluttonK commented 1 year ago

Thank you very much， It helps a lot!!!

K-H-Ismail commented 1 year ago

You're welcome,

I'm closing this issue, but feel free to reopen it if you have any questions or comments.